Lecture Constructive Algorithms for Discrepancy Minimization
نویسندگان
چکیده
In terms of applications, the min discrepancy problem appears in many varied areas of both Computer Science (Computational Geometry, Comb. Optimization, Monte-Carlo simulation, Machine learning, Complexity, Pseudo-Randomness) and Mathematics (Dynamical Systems, Combinatorics, Mathematical Finance, Number Theory, Ramsey Theory, Algebra, Measure Theory,...). One may consult any of the following books [Cha01, AS00, Mat10] for an in depth view of the subject.
منابع مشابه
Lecture 3 : Constructive Bounds on Discrepancy
In previous lectures we saw a constructive proof of the Lovasz Local Lemma and an application to a variant of the max-min allocations problem. In this lecture we will continue the topic of algorithmic versions of existential theorems with a recent result due to Bansal [Ban10] that makes Spencer’s [Spe85] and Srinavasan’s [Sri97] bounds on discrepancy of set systems constructive. What makes Bans...
متن کاملLow Discrepancy Sequences and Learning
The Discrepancy Method is a constructive method for proving upper bounds that has received a lot of attention in recent years. In this paper we revisit a few important results, and show how it can be applied to problems in Machine Learning such as the Empirical Risk Minimization and Risk Estimation by exploiting connections with combinatorial dimension theory.
متن کاملConstructive Discrepancy Minimization with Hereditary L2 Guarantees
In discrepancy minimization problems, we are given a family of sets S = {S1, . . . , Sm}, with each Si ∈ S a subset of some universe U = {u1, . . . , un} of n elements. The goal is to find a coloring χ : U → {−1,+1} of the elements of U such that each set S ∈ S is colored as evenly as possible. Two classic measures of discrepancy are l∞-discrepancy defined as disc∞(S , χ) := maxS∈S | ∑ ui∈S χ(u...
متن کاملDeterministic Discrepancy Minimization via the Multiplicative Weight Update Method
A well-known theorem of Spencer shows that any set system with n sets over n elements admits a coloring of discrepancy O( √ n). While the original proof was non-constructive, recent progress brought polynomial time algorithms by Bansal, Lovett and Meka, and Rothvoss. All those algorithms are randomized, even though Bansal’s algorithm admitted a complicated derandomization. We propose an elegant...
متن کاملDomain Adaptation: Learning Bounds and Algorithms
This paper addresses the general problem of domain adaptation which arises in a variety of applications where the distribution of the labeled sample available somewhat differs from that of the test data. Building on previous work by Ben-David et al. (2007), we introduce a novel distance between distributions, discrepancy distance, that is tailored to adaptation problems with arbitrary loss func...
متن کامل